@inproceedings{feng-etal-2024-well,
title = "Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification",
author = "Feng, Huawen and
Yan, Jingsong and
Liu, Junlong and
Zheng, Junhao and
Ma, Qianli",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1515/",
pages = "17433--17443",
abstract = "Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text. Discriminative methods usually incorporate the hierarchical structure information into the encoding process, while generative methods decode the features according to it. However, the data distribution varies widely among different categories of samples, but current methods ignore the data imbalance, making the predictions biased and susceptible to error propagation. In this paper, we propose an **IM**plicitly **A**ugmented **G**enerativ **E** framework with distribution modification for hierarchical text classification (**IMAGE**). Specifically, we translate the distributions of original samples along various directions through implicit augmentation to get more diverse data. Furthermore, given the scarcity of the samples of tail classes, we adjust their distributions by transferring knowledge from other classes in label space. In this way, the generative framework learns a better beginning of the feature sequence without a prediction bias and avoids being misled by its wrong predictions for head classes. Experimental results show that **IMAGE** obtains competitive results compared with state-of-the-art methods and prove its superiority on unbalanced data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2024-well">
<titleInfo>
<title>Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huawen</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingsong</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junlong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianli</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text. Discriminative methods usually incorporate the hierarchical structure information into the encoding process, while generative methods decode the features according to it. However, the data distribution varies widely among different categories of samples, but current methods ignore the data imbalance, making the predictions biased and susceptible to error propagation. In this paper, we propose an **IM**plicitly **A**ugmented **G**enerativ **E** framework with distribution modification for hierarchical text classification (**IMAGE**). Specifically, we translate the distributions of original samples along various directions through implicit augmentation to get more diverse data. Furthermore, given the scarcity of the samples of tail classes, we adjust their distributions by transferring knowledge from other classes in label space. In this way, the generative framework learns a better beginning of the feature sequence without a prediction bias and avoids being misled by its wrong predictions for head classes. Experimental results show that **IMAGE** obtains competitive results compared with state-of-the-art methods and prove its superiority on unbalanced data.</abstract>
<identifier type="citekey">feng-etal-2024-well</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1515/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17433</start>
<end>17443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification
%A Feng, Huawen
%A Yan, Jingsong
%A Liu, Junlong
%A Zheng, Junhao
%A Ma, Qianli
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F feng-etal-2024-well
%X Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text. Discriminative methods usually incorporate the hierarchical structure information into the encoding process, while generative methods decode the features according to it. However, the data distribution varies widely among different categories of samples, but current methods ignore the data imbalance, making the predictions biased and susceptible to error propagation. In this paper, we propose an **IM**plicitly **A**ugmented **G**enerativ **E** framework with distribution modification for hierarchical text classification (**IMAGE**). Specifically, we translate the distributions of original samples along various directions through implicit augmentation to get more diverse data. Furthermore, given the scarcity of the samples of tail classes, we adjust their distributions by transferring knowledge from other classes in label space. In this way, the generative framework learns a better beginning of the feature sequence without a prediction bias and avoids being misled by its wrong predictions for head classes. Experimental results show that **IMAGE** obtains competitive results compared with state-of-the-art methods and prove its superiority on unbalanced data.
%U https://aclanthology.org/2024.lrec-main.1515/
%P 17433-17443
Markdown (Informal)
[Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification](https://aclanthology.org/2024.lrec-main.1515/) (Feng et al., LREC-COLING 2024)
ACL